Skrr skips and reuses sub-layers of the T5 text encoder in text-to-image models, cutting memory by roughly 36% at about 42% sparsity while keeping FID and CLIP scores near the dense model.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
Skrr skips and reuses sub-layers of the T5 text encoder in text-to-image models, cutting memory by roughly 36% at about 42% sparsity while keeping FID and CLIP scores near the dense model.